© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11555
    Prev
    Next
    INDEX
    Explanations

    phrases related to directing attention or effort towards a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "focus on" in relation to various topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.86
    listed
    -0.81
    ©¶æ¥µ
    -0.75
    zynski
    -0.74
    ugh
    -0.73
    RIP
    -0.73
    alan
    -0.72
    soType
    -0.71
    UP
    -0.71
    sup
    -0.71
    POSITIVE LOGITS
     improving
    1.42
     maximizing
    1.31
     preserving
    1.29
     protecting
    1.21
     optimizing
    1.21
     ensuring
    1.21
     achieving
    1.19
     solving
    1.18
     preventing
    1.18
     maintaining
    1.18
    Activations Density 0.138%

    No Known Activations